|Publication number||US7093024 B2|
|Application number||US 09/965,005|
|Publication date||Aug 15, 2006|
|Filing date||Sep 27, 2001|
|Priority date||Sep 27, 2001|
|Also published as||US20030061379|
|Publication number||09965005, 965005, US 7093024 B2, US 7093024B2, US-B2-7093024, US7093024 B2, US7093024B2|
|Inventors||David F. Craddock, David Arlen Elko, Thomas Anthony Gregg, Gregory Francis Pfister, Renato John Recio, Donald William Schmidt|
|Original Assignee||International Business Machines Corporation|
|Export Citation||BiBTeX, EndNote, RefMan|
|Patent Citations (18), Non-Patent Citations (2), Referenced by (101), Classifications (9), Legal Events (5)|
|External Links: USPTO, USPTO Assignment, Espacenet|
1. Technical Field
The present invention relates generally to communications between computer systems and, more particularly, to a method and apparatus for a single InfiniBand chip which can support end node partitioning by enabling virtualization of an InfiniBand Host Channel Adapter (HCA) and router components.
2. Description of Related Art
In a System Area Network (SAN), the hardware provides a message passing mechanism which can be used for Input/Output devices (I/O) and interprocessor communications between general computing nodes (IPC). Consumers access SAN message passing hardware by posting send/receive messages to send/receive work queues on a SAN channel adapter (CA). The send/receive work queues (WQ) are assigned to a consumer as a queue pair (QP). The messages can be sent over five different defined transport types: Reliable Connected (RC), Reliable datagram (RD), Unreliable Connected (UC), Unreliable Datagram (UD), and Raw Datagram (RawD). In addition, there is a set of manufacturer definable operation codes that allow for different companies to define custom packets that still have the same routing header layouts. Consumers retrieve the results of the defined messages from a completion queue (CQ) through SAN send and receive work completions (WC). The manufacturer definable operations are not defined as to whether or not they use the same queuing structure as the defined packet types. Regardless of the packet type, the source channel adapter takes care of segmenting outbound messages and sending them to the destination. The destination channel adapter takes care of reassembling inbound messages and placing them in the memory space designated by the destination's consumer. Two channel adapter types are present, a host channel adapter (HCA) and a target channel adapter (TCA). The host channel adapter is used by general purpose computing nodes to access the SAN fabric. Consumers use SAN verbs to access host channel adapter functions. The software that interprets verbs and directly accesses the channel adapter is known as the channel interface (CI).
The InfiniBand network is broken up into separate autonomous management units (each containing multiple IB nodes) called subnets. InfiniBand components are assigned a Global Identifier (GID) during initialization. The GID is used to uniquely identify the target component both within and across IB subnets. Communications among components that reside in different IB subnets are provided by including an additional header called a Global Routing Header (GRH) being included in every IB packet, defining both the source and the destination addresses/nodes. These additional addresses allow routers that span subnets to determine the path that is to be taken for the packet to reach its ultimate destination (i.e. target GID). Unlike within subnet communications where a direct path can be obtained to the target (i.e. LID), cross subnet communications typically requires one or more hops through intermediate router(s).
InfiniBand does not define a mechanism that allows a single physical IB node (e.g. a host channel adapter) to transparently implement one or more entire IB subnets. However, a single physical IB node transparently implementing one or more entire IB subnets becomes a highly desirable feature, especially for environments where a large number of servers (e.g., Linux) are implemented within a single physical machine (e.g., IBM's z/VM).
Therefore, a mechanism is needed in environments containing a large number of servers to allow economies of scale cost reductions to be achieved by sharing a single physical IB node across potentially many server images. This mechanism must not incur significant mainline processing overheads and must allow the resulting overall solution to be competitive within the marketplace.
The present invention provides a mechanism for allowing a single physical IB node to virtualize a plurality of host channel adapters. This includes providing the appearance of both a router and multiple virtual HCA's residing behind that router, to the external REAL subnet components. Each virtual host channel adapter will have unique access control levels. One or more InfiniBand subnets are virtualized in such a way that nodes residing both within the virtual subnets and in separate physical subnets are completely unaware of the virtualization. This virtualization of InfiniBand subnets significantly increases the horizontal scaling capabilities of a single InfiniBand physical component, while at the same time provides “native” network throughput for all the virtual hosts.
The novel features believed characteristic of the invention are set forth in the appended claims. The invention itself, however, as well as a preferred mode of use, further objectives and advantages thereof, will best be understood by reference to the following detailed description of an illustrative embodiment when read in conjunction with the accompanying drawings, wherein:
The present invention provides a network computing system having end nodes, switches, routers, and links interconnecting these components. The end nodes segment the message into packets and transmit the packets over the links. The switches and routers interconnect the end nodes and route the packets to the appropriate end node. The end nodes reassemble the packets into a message at the destination.
With reference now to the figures and in particular with reference to
SAN 100 is a high-bandwidth, low-latency network interconnecting nodes within the network computing system. A node is any component attached to one or more links of a network and forming the origin and/or destination of messages within the network. In the depicted example, SAN 100 includes nodes in the form of host processor node 102, host processor node 104, redundant array independent disk (RAID) subsystem node 106, I/O chassis node 108, and PCI I/O Chassis node 184. The nodes illustrated in
A message, as used herein, is an application-defined unit of data exchange, which is a primitive unit of communication between cooperating processes. A packet is one unit of data encapsulated by a networking protocol headers and/or trailer. The headers generally provide control and routing information for directing the frame through SAN. The trailer generally contains control and cyclic redundancy check (CRC) data for ensuring packets are not delivered with corrupted contents.
SAN 100 contains the communications and management infrastructure supporting both I/O and interprocessor communications (IPC) within a network computing system. The SAN 100 shown in
The SAN 100 in
In one embodiment, a link is a full duplex channel between any two network fabric elements, such as endnodes, switches, or routers. Example suitable links include, but are not limited to, copper cables, optical cables, and printed circuit copper traces on backplanes and printed circuit boards.
For reliable service types, endnodes, such as host processor endnodes and I/O adapter endnodes, generate request packets and return acknowledgment packets. Switches and routers pass packets along, from the source to the destination. Except for the variant CRC trailer field which is updated at each stage in the network, switches pass the packets along unmodified. Routers update the variant CRC trailer field and modify other fields in the header as the packet is routed.
In SAN 100 as illustrated in
In one embodiment, a host channel adapter is implemented in hardware. In this implementation, the host channel adapter hardware offloads much of central processing unit and I/O adapter communication overhead. This hardware implementation of the host channel adapter also permits multiple concurrent communications over a switched network without the traditional overhead associated with communicating protocols. In one embodiment, the host channel adapters and SAN 100 in
The I/O chassis 108 in
In this example, RAID subsystem node 106 in
PCI I/O Chassis node 184 includes a TCA 186 and multiple PCI Input/Output Adapters (IOA) 190–192 connected to TCA 186 via PCI bus 188. In these examples, the IOAs take the form of adapter cards. Example adapter cards illustrated in
Similarly, store and load requests from a processor, such as, for example, CPU 126, to a PCI IOA, such as PCI IOA 190 or 192 are encapsulated into a data packet by the HCA 118 for transmission to the TCA 186 corresponding to the appropriate PCI IOA 190 or 192 across SAN fabric 100. The TCA 186 decodes the data packet to retrieve the PCI transmission and transmits the PCI store or load request and data to PCI IOA 190 or 192 via PCI bus 188. If the request is a load request, the TCA 186 then receives a response from the PCI IOA 190 or 192 which the TCA encapsulates into a data packet and transmits over the SAN fabric 100 to HCA 118 which decodes the data packet to retrieve the PCI data and commands and sends the PCI data and commands to the requesting CPU 126. Thus, PCI adapters may be connected to the SAN fabric 100 of the present invention.
SAN 100 handles data communications for I/O and interprocessor communications. SAN 100 supports high-bandwidth and scalability required for I/O and also supports the extremely low latency and low CPU overhead required for interprocessor communications. User clients can bypass the operating system kernel process and directly access network communication hardware, such as host channel adapters, which enable efficient message passing protocols. SAN 100 is suited to current computing models and is a building block for new forms of I/O and computer cluster communication. Further, SAN 100 in
In this example, host processor node 200 shown in
Consumers 208–208 transfer messages to the SAN via the verbs interface 222 and message and data service 224. A verbs interface is essentially an abstract description of the functionality of a host channel adapter. An operating system may expose some or all of the verb functionality through its programming interface. Basically, this interface defines the behavior of the host. Additionally, host processor node 200 includes a message and data service 224, which is a higher level interface than the verb layer and is used to process messages and data received through channel adapter 210 and channel adapter 212. Message and data service 224 provides an interface to consumers 208–208 to process messages and other data. In addition, the channel adapter 210 and channel adapter 212 may receive load and store instructions from the processors which are targeted for PCI IOAs attached to the SAN. These bypass the verb layer, as shown in
A single channel adapter, such as the host channel adapter 300A shown in
Channel adapters, switches, and routers employ multiple virtual lanes within a single physical link. As illustrated in
Virtual lanes are employed for numerous reasons, some of which are as follows: Virtual lanes provide QoS. In one example embodiment, certain virtual lanes are reserved for high priority traffic to provide QoS.
Virtual lanes provide deadlock avoidance. Virtual lanes allow topologies that contain loops to send packets across all physical links and still be assured the loops won't cause back pressure dependencies that might result in deadlock.
Virtual lanes alleviate head-of-line blocking. When a switch has no more credits available for packets that utilize a given virtual lane, packets utilizing a different virtual lane that has sufficient credits are allowed to make forward progress.
Send work queue 402 contains work queue elements (WQEs) 422–428, describing data to be transmitted on the SAN fabric. Receive work queue 400 contains work queue elements (WQEs) 416–420, describing where to place incoming channel semantic data from the SAN fabric. A work queue element is processed by hardware 408 in the host channel adapter.
The verbs also provide a mechanism for retrieving completed work from completion queue 404. As shown in
Example work requests supported for the send work queue 402 shown in
A remote direct memory access (RDMA) read work request provides a memory semantic operation to read a virtually contiguous memory space on a remote node. A memory space can either be a portion of a memory region or portion of a memory window. A memory region references a previously registered set of virtually contiguous memory addresses defined by a virtual address and length. A memory window references a set of virtually contiguous memory addresses which have been bound to a previously registered region.
The RDMA Read work request reads a virtually contiguous memory space on a remote endnode and writes the data to a virtually contiguous local memory space. Similar to the send work request, virtual addresses used by the RDMA Read work queue element to reference the local data segments are in the address context of the process that created the local queue pair. For example, work queue element 416 in receive work queue 400 references data segment 1 444, data segment 2 446, and data segment 448. The remote virtual addresses are in the address context of the process owning the remote queue pair targeted by the RDMA Read work queue element.
A RDMA Write work queue element provides a memory semantic operation to write a virtually contiguous memory space on a remote node. The RDMA Write work queue element contains a scatter list of local virtually contiguous memory spaces and the virtual address of the remote memory space into which the local memory spaces are written.
A RDMA FetchOp work queue element provides a memory semantic operation to perform an atomic operation on a remote word. The RDMA FetchOp work queue element is a combined RDMA Read, Modify, and RDMA Write operation. The RDMA FetchOp work queue element can support several read-modify-write operations, such as Compare and Swap if equal.
A bind (unbind) remote access key (R_Key) work queue element provides a command to the host channel adapter hardware to modify (destroy) a memory window by associating (disassociating) the memory window to a memory region. The R_Key is part of each RDMA access and is used to validate that the remote process has permitted access to the buffer.
In one embodiment, receive work queue 400 shown in
For interprocessor communications, a user-mode software process transfers data through queue pairs directly from where the buffer resides in memory. In one embodiment, the transfer through the queue pairs bypasses the operating system and consumes few host instruction cycles. Queue pairs permit zero processor-copy data transfer with no operating system kernel involvement. The zero processor-copy data transfer provides for efficient support of high-bandwidth and low-latency communication.
When a queue pair is created, the queue pair is set to provide a selected type of transport service. In one embodiment, a network computing system implementing the present invention supports four types of transport services.
Reliable and Unreliable connected services associate a local queue pair with one and only one remote queue pair. Connected services require a process to create a queue pair for each process which is to communicate with over the SAN fabric. Thus, if each of N host processor nodes contain P processes, and all P processes on each node wish to communicate with all the processes on all the other nodes, each host processor node requires P2×(N−1) queue pairs. Moreover, a process can connect a queue pair to another queue pair on the same host channel adapter.
Reliable datagram service associates a local end-end (EE) context with one and only one remote end-end context. The reliable datagram service permits a client process of one queue pair to communicate with any other queue pair on any other remote node. At a receive work queue, the reliable datagram service permits incoming messages from any send work queue on any other remote node. The reliable datagram service greatly improves scalability because the reliable datagram service is connectionless. Therefore, an endnode with a fixed number of queue pairs can communicate with far more processes and endnodes with a reliable datagram service than with a reliable connection transport service. For example, if each of N host processor nodes contain P processes, and all P processes on each node wish to communicate with all the processes on all the other nodes, the reliable connection service requires p2×(N−1 queue pairs on each node. By comparison, the connectionless reliable datagram service only requires P queue pairs+(N−1) EE contexts on each node for exactly the same communications.
The unreliable datagram service is connectionless. The unreliable datagram service is employed by management applications to discover and integrate new switches, routers, and endnodes into a given network computing system. The unreliable datagram service does not provide the reliability guarantees of the reliable connection service and the reliable datagram service. The unreliable datagram service accordingly operates with less state information maintained at each endnode.
Additionally, transport header 518 also provides information such as the operation code, packet sequence number, and partition for data packet 512. The operating code identifies whether the packet is the first, last, intermediate, or only packet of a message. The operation code also specifies whether the operation is a send RDMA write, read, or atomic. The packet sequence number is initialized when communications is established and increments each time a queue pair creates a new packet. Ports of an endnode may be configured to be members of one or more possibly overlapping sets called partitions.
Physical component 600 in
In the example transactions, host processor node 602 includes client process A 614. Host processor node 604 includes a client process B 616. Client process A 614 interacts with host channel adapter hardware 606 through queue pair 618, completion queue 630 and Translation Protection Table (TPT) 632. Client process B 616 interacts with host channel adapter 608 through queue pair 620, completion queue 634 and TPT 636. Queue pair 618, queue pair 620, completion queue 630, completion queue 634, TPT 632 and TPT 636 are data structures. Queue pair 618 includes a send work queue 622 and a receive work queue 624. Queue pair 620 includes a send work queue 626 and a receive work queue 628. Completion queues 630 and 634 consist of a single completion queue. TPTs 632 and 636 consist of a memory address translation and protection table.
A multi-function chip may provide a resource configuration and allocation interface to software, firmware or a hardware state machine which will execute as part of physical component 600. The resource configuration and allocation interface allows software, firmware, or hardware state machines to set an operating policy for the virtual HCAs and routers, for example HCAs 606 and 608 in
In one embodiment, there are two subnets of note, a real subnet 652, and a separate virtual subnet 610 that resides behind a multi-function InfiniBand chip. However, the present invention allows for multiple subnets to be virtualized in a similar fashion. At this point it is important to note that it is assumed that no subnets reside behind any virtual subnets (e.g., a virtual subnet is a leaf subnet within a subnet hierarchy).
In a preferred embodiment, only host channel adapters (HCAs) reside within a virtual subnet. However, virtualization of multiple devices (e.g., TCAs) may also reside behind a single IB node.
The appearance of separate virtual subnets is employed to cause global routing headers (GRHs) to be added to incoming and outgoing data packets. A GRH contains fields for routing the packet between subnets. These GRHs are sometimes used by inbound processing of a software router (e.g., router 612) to qualify specific virtual servers/virtual HCAs that reside behind a single multi-function chip. All nodes residing within a physical subnet (e.g., subnet 652) use standard router based techniques to communicate with virtual HCAs (e.g., HCAs 606 and 608) residing behind a virtual router, such as router 612 in
In general, a router, such as router 612, is responsible for receiving data packets from one link and transmitting the data packets over another link that moves the data packets closer to their ultimate destination. This transmission of the data packets closer to their ultimate destination includes determining which link the packet needs to be forwarded to. This determination is made by using the target GID to query the subnet manager 660 in the newly reached subnet (e.g., subnet 610) when a request is initiated from within subnet 652, to find out how to reach the packet's ultimate destination. Each cross-IB subnet packet contains a GRH that defines the packet's ultimate destination GID. The information returned from the subnet manager includes the specific node's LID (i.e. the next hop) that is to be targeted within the new subnet so that a Local Router Header (LRH) can be formed. The router then replaces the original LRH of the packet being forwarded with the new LRH formed above and sends the packet over the appropriate new link. The LID targeted by the router in the new LRH may be either that of another router or the ultimate destination of the data packet as defined in the GRH.
When an entire subnet is virtualized, much of the traditional router processing and overhead, specifically the destination lookup and packet forwarding, can be bypassed (as described below).
Standard IB states that a physical subnet manager (e.g., subnet manager 650) supports at least static routes that define routers that are to be used to reach different subnets. A physical subnet administration query process includes matching the subnet portion of a target global identifier (GID) with these static routes when the target GID does not reside within the physical subnet 652. When a subnet match is found, path information describing a local identifier (LID) of the router is returned to the querying process. As InfiniBand processing dictates, a requesting node then builds data packets consisting of a LRH for the router, such as, router 612, followed by the GRH of the target destination, such as GID 668.
In order to minimize the development costs associated with chip design and development, a multi-function chip only requires small changes from a standard HCA design to enable software virtualization of entire subnet(s). One example of this enablement of software utilization is that the multi-function chip presents itself as a “router” to the physical subnet manager, instead of a HCA. Access is then provided to the physical fabric for a collection of virtual servers, otherwise called “guests,” via that router.
The software behind the multi-function chip implements functionality of the router in addition to providing a subset of Subnet Manager (SM) functions for the subnets being virtualized. This software acts as a “Hypervisor” for the operating system images and virtual HCAs being supported. Due to chip design, the router function is implemented in such a way that the router is only involved in control-flow processing, such as connection setup, not mainline data flow processing. This is possible because each guest both resides behind a software router (via virtualized control flow QPs) and has direct access to the multi-function chip that resides on the physical subnet (all physical QPs other than the control flow QP). “Subnet Facade” may be used to describe this capability in which, from a management prospective, the guests reside within a separate subnet. However, from a mainline data flow perspective, router overheads are bypassed.
A single multi-function chip when combined with appropriate software performs both the network layer packet relay function of a router for traffic to and from the virtual subnets, and the QP end node transport layer function of a HCA for multiple guests. Virtual HCAs (e.g., virtual HCAs 606 and 608) are conceptual groupings of the physical QP resources implemented by the multi-function chip. All standard HCA functionality (e.g., verbs, RDMA, etc.) are provided by the multi-function chip directly to the guests, via these physical QPs, even though the guests logically reside behind the router. Once communications are established, data sent to/from guests is performed at native (i.e. non-cross-subnet) IB node throughput levels.
The Hypervisor provides the appearance of multiple virtual HCAs to the guests. These virtual HCAs have the same resource attributes as physical HCAs (e.g., HCA ports, P_Key table, etc.). However, since the HCAs are being virtualized, the Hypervisor can provide the ability to dynamically create these virtual HCAs as new guests are defined. The Hypervisor virtualizes the following activities: bootstrap defining of the virtual HCAs that are accessible to guests or operating system images; virtual HCA open processing; and creation of control flow virtual QPs (e.g. QP1).
Physical chip resource allocation, such as, for example, QP allocation, is shared across the multiple guests being virtualized. However, once allocated, individual resources are dedicated to a single guest. A single physical resource name space is shared among all guests. This means that once a physical QP number, for example “6”, is assigned to a given guest, the number “6” may not be reused until the guest owning the number “6” frees it. The dedication of physical resources to a single guest is standard processing from the chip's perspective because occurrence of the guest virtualization is transparent to the chip. Using this model of chip resource allocation allows the chip to ignore the GRH information resident in arriving packets and instead use only the target physical QP number, which is now known to be unique across all subnets being virtualized by the multi-function chip. This implementation bypasses all of the look-up/forwarding overhead associated with a traditional router for mainline data flow processing.
Consideration is required when individual chip resources are assigned to allow guest level HCA access rights to be enforced upon guest initiated activities (e.g., on a QP or Memory Region basis) and guest level interrupts to occur for HCA initiated activities (e.g., on a per CQ basis). The allocation of chip resources is performed on either a per-request basis or as blocks of resources. This assignment of the chip's resources could either be static or dynamic. Dynamic assignment per request provides an optimal physical resource utilization.
The Hypervisor also provides a subset of Subnet Manager functions for the guests and virtual HCAs residing within the virtual subnet. These functions include, for example, assigning GIDs and GUIDs to the guests and assigning virtual LIDs for communication among guests within the virtual subnet.
The present invention simplifies complexities associated with traditional subnet environments because, in the present invention, an entire subnet is implemented in software. An example of this simplification is that a P_Key structure of a physical subnet is used in the virtual subnet. This allows access rights of guests to be clearly mapped to the physical subnet devices and hosts.
As is noted above, the control-flow QP (e.g., QP1) resource is virtualized by the Hypervisor. The single chip implemented control-flow QP must be shared by all guests in such a way that each guest perceives that it has its own separate control-flow QP. This sharing is performed by the software virtual router demultiplexing arriving control-flow packets based upon the target GID, to the appropriate virtualized guest specific control-flow QP. This control-flow processing is the only time that the GRH included in all cross-subnet packets is accessed.
It is important to note that while the present invention has been described in the context of a fully functioning data processing system, those of ordinary skill in the art will appreciate that the processes of the present invention are capable of being distributed in the form of a computer readable medium of instructions and a variety of forms and that the present invention applies equally regardless of the particular type of signal bearing media actually used to carry out the distribution. Examples of computer readable media include recordable-type media, such as a floppy disk, a hard disk drive, a RAM, CD-ROMs, DVD-ROMs, and transmission-type media, such as digital and analog communications links, wired or wireless communications links using transmission forms, such as, for example, radio frequency and light wave transmissions. The computer readable media may take the form of coded formats that are decoded for actual use in a particular data processing system.
The description of the present invention has been presented for purposes of illustration and description, and is not intended to be exhaustive or limited to the invention in the form disclosed. Many modifications and variations will be apparent to those of ordinary skill in the art. The embodiment was chosen and described in order to best explain the principles of the invention, the practical application, and to enable others of ordinary skill in the art to understand the invention for various embodiments with various modifications as are suited to the particular use contemplated.
|Cited Patent||Filing date||Publication date||Applicant||Title|
|US5822319 *||May 17, 1996||Oct 13, 1998||Kabushiki Kaisha Toshiba||Router device and datagram transfer method for data communication network system|
|US6085238 *||Apr 22, 1997||Jul 4, 2000||Matsushita Electric Works, Ltd.||Virtual LAN system|
|US6438128 *||May 8, 2001||Aug 20, 2002||International Business Machines Corporation||Alternate use of data packet fields to convey information|
|US6438612 *||Sep 11, 1998||Aug 20, 2002||Ssh Communications Security, Ltd.||Method and arrangement for secure tunneling of data between virtual routers|
|US6459698 *||Jun 18, 2001||Oct 1, 2002||Advanced Micro Devices, Inc.||Supporting mapping of layer 3 priorities in an infiniband ™ network|
|US6578122 *||Mar 1, 2001||Jun 10, 2003||International Business Machines Corporation||Using an access key to protect and point to regions in windows for infiniband|
|US6594712 *||Oct 20, 2000||Jul 15, 2003||Banderacom, Inc.||Inifiniband channel adapter for performing direct DMA between PCI bus and inifiniband link|
|US6597699 *||Sep 28, 1999||Jul 22, 2003||Telefonaktiebolaget Lm Ericsson (Publ)||Quality of service management in a packet data router system having multiple virtual router instances|
|US6674756 *||Feb 23, 2000||Jan 6, 2004||Alcatel||Multi-service network switch with multiple virtual routers|
|US6687220 *||Sep 28, 1999||Feb 3, 2004||Ericsson Inc.||Quality of service management in a packet data router having multiple virtual router instances|
|US6694361 *||Jun 30, 2000||Feb 17, 2004||Intel Corporation||Assigning multiple LIDs to ports in a cluster|
|US6717913 *||Feb 23, 2000||Apr 6, 2004||Alcatel||Multi-service network switch with modem pool management|
|US6744765 *||Aug 24, 2000||Jun 1, 2004||Sun Microsystems, Inc.||Mechanism for completing messages in memory|
|US6789118 *||Feb 23, 2000||Sep 7, 2004||Alcatel||Multi-service network switch with policy based routing|
|US6850531 *||Feb 23, 2000||Feb 1, 2005||Alcatel||Multi-service network switch|
|US6885667 *||Dec 26, 2000||Apr 26, 2005||Cisco Technology, Inc.||Redirection to a virtual router|
|US6889380 *||Jun 30, 2000||May 3, 2005||Intel Corporation||Delaying loading of host-side drivers for cluster resources to avoid communication failures|
|US6914905 *||Jun 16, 2000||Jul 5, 2005||Extreme Networks, Inc.||Method and system for VLAN aggregation|
|1||*||Lopez et al. "Deadlock-free routing in infiniband through destination renaming" 2001 IEEE, pp. 427-434 (publication date: Sep. 3-7, 2001).|
|2||*||Sancho et al. "Effective strategy to compute forwarding tables for infiniband network" 2001 IEEE, pp. 48-57 (publication date: Sep. 3-7, 2001).|
|Citing Patent||Filing date||Publication date||Applicant||Title|
|US7286544 *||Jul 25, 2002||Oct 23, 2007||Brocade Communications Systems, Inc.||Virtualized multiport switch|
|US7401126 *||Mar 23, 2001||Jul 15, 2008||Neteffect, Inc.||Transaction switch and network interface adapter incorporating same|
|US7564869||Jul 21, 2009||Cisco Technology, Inc.||Fibre channel over ethernet|
|US7602720||Jun 16, 2005||Oct 13, 2009||Cisco Technology, Inc.||Active queue management methods and devices|
|US7633955||Jan 19, 2006||Dec 15, 2009||Habanero Holdings, Inc.||SCSI transport for fabric-backplane enterprise servers|
|US7664110||Feb 12, 2005||Feb 16, 2010||Habanero Holdings, Inc.||Input/output controller for coupling the processor-memory complex to the fabric in fabric-backplane interprise servers|
|US7685281||Feb 12, 2005||Mar 23, 2010||Habanero Holdings, Inc.||Programmatic instantiation, provisioning and management of fabric-backplane enterprise servers|
|US7698388 *||Oct 29, 2007||Apr 13, 2010||Aventail Llc||Secure access to remote resources over a network|
|US7757033||Jul 12, 2004||Jul 13, 2010||Habanero Holdings, Inc.||Data exchanges among SMP physical partitions and I/O interfaces enterprise servers|
|US7770222||Oct 29, 2007||Aug 3, 2010||Aventail Llc||Creating an interrogation manifest request|
|US7779469||Oct 29, 2007||Aug 17, 2010||Aventail Llc||Provisioning an operating environment of a remote computer|
|US7782905||Feb 17, 2006||Aug 24, 2010||Intel-Ne, Inc.||Apparatus and method for stateless CRC calculation|
|US7801125||Jun 14, 2005||Sep 21, 2010||Cisco Technology, Inc.||Forwarding table reduction and multipath network forwarding|
|US7802000 *||May 1, 2006||Sep 21, 2010||Vmware||Virtual network in server farm|
|US7827590||Oct 14, 2005||Nov 2, 2010||Aventail Llc||Controlling access to a set of resources in a network|
|US7830793||Mar 30, 2005||Nov 9, 2010||Cisco Technology, Inc.||Network device architecture for consolidating input/output and reducing latency|
|US7831710||Feb 25, 2008||Nov 9, 2010||International Business Machines Corporation||Communication of offline status between computer systems|
|US7843906||Oct 22, 2005||Nov 30, 2010||Habanero Holdings, Inc.||Storage gateway initiator for fabric-backplane enterprise servers|
|US7843907||Oct 22, 2005||Nov 30, 2010||Habanero Holdings, Inc.||Storage gateway target for fabric-backplane enterprise servers|
|US7849232||Feb 17, 2006||Dec 7, 2010||Intel-Ne, Inc.||Method and apparatus for using a single multi-function adapter with different operating systems|
|US7860097||Feb 12, 2005||Dec 28, 2010||Habanero Holdings, Inc.||Fabric-backplane enterprise servers with VNICs and VLANs|
|US7860961||Feb 12, 2005||Dec 28, 2010||Habanero Holdings, Inc.||Real time notice of new resources for provisioning and management of fabric-backplane enterprise servers|
|US7870306||Aug 31, 2006||Jan 11, 2011||Cisco Technology, Inc.||Shared memory message switch and cache|
|US7873693||Feb 12, 2005||Jan 18, 2011||Habanero Holdings, Inc.||Multi-chassis fabric-backplane enterprise servers|
|US7889762||Jan 19, 2007||Feb 15, 2011||Intel-Ne, Inc.||Apparatus and method for in-line insertion and removal of markers|
|US7895462||Mar 19, 2008||Feb 22, 2011||International Business Machines Corporation||Managing recovery and control of a communications link via out-of-band signaling|
|US7913024 *||Dec 9, 2008||Mar 22, 2011||International Business Machines Corporation||Differentiating traffic types in a multi-root PCI express environment|
|US7930443 *||Apr 19, 2011||Juniper Networks, Inc.||Router having routing engine software instance and interface controller software instance on a single processor|
|US7949721||Feb 25, 2008||May 24, 2011||International Business Machines Corporation||Subnet management discovery of point-to-point network topologies|
|US7953903||Feb 12, 2005||May 31, 2011||Habanero Holdings, Inc.||Real time detection of changed resources for provisioning and management of fabric-backplane enterprise servers|
|US7961621||Oct 11, 2005||Jun 14, 2011||Cisco Technology, Inc.||Methods and devices for backward congestion notification|
|US7962564||Feb 25, 2008||Jun 14, 2011||International Business Machines Corporation||Discovery of a virtual topology in a multi-tasking multi-processor environment|
|US7969971 *||Mar 18, 2005||Jun 28, 2011||Cisco Technology, Inc.||Ethernet extension for the data center|
|US7990994 *||Oct 22, 2005||Aug 2, 2011||Habanero Holdings, Inc.||Storage gateway provisioning and configuring|
|US8005983||Oct 29, 2007||Aug 23, 2011||Aventail Llc||Rule-based routing to resources through a network|
|US8009589||Feb 25, 2008||Aug 30, 2011||International Business Machines Corporation||Subnet management in virtual host channel adapter topologies|
|US8019830 *||Apr 16, 2008||Sep 13, 2011||Mark Thompson||Methods and apparatus for acquiring file segments|
|US8032664||Sep 2, 2010||Oct 4, 2011||Intel-Ne, Inc.||Method and apparatus for using a single multi-function adapter with different operating systems|
|US8042004||Feb 25, 2008||Oct 18, 2011||International Business Machines Corporation||Diagnosing communications between computer systems|
|US8065279||Feb 25, 2008||Nov 22, 2011||International Business Machines Corporation||Performance neutral heartbeat for a multi-tasking multi-processor environment|
|US8078743||Feb 17, 2006||Dec 13, 2011||Intel-Ne, Inc.||Pipelined processing of RDMA-type network transactions|
|US8078756 *||Jun 3, 2003||Dec 13, 2011||Cisco Technology, Inc.||Computing a path for an open ended uni-directional path protected switched ring|
|US8090827||Jan 19, 2010||Jan 3, 2012||Aventail Llc||Secure access to remote resources over a network|
|US8121038||Aug 21, 2007||Feb 21, 2012||Cisco Technology, Inc.||Backward congestion notification|
|US8144582||Dec 30, 2008||Mar 27, 2012||International Business Machines Corporation||Differentiating blade destination and traffic types in a multi-root PCIe environment|
|US8145785||Feb 12, 2005||Mar 27, 2012||Habanero Holdings, Inc.||Unused resource recognition in real time for provisioning and management of fabric-backplane enterprise servers|
|US8149710||Jul 5, 2007||Apr 3, 2012||Cisco Technology, Inc.||Flexible and hierarchical dynamic buffer allocation|
|US8160094||Apr 17, 2012||Cisco Technology, Inc.||Fibre channel over ethernet|
|US8176219||Apr 18, 2011||May 8, 2012||Juniper Networks, Inc.||Router having routing engine software instance and interaface controller software instance on a single processor|
|US8223745 *||Dec 1, 2005||Jul 17, 2012||Oracle America, Inc.||Adding packet routing information without ECRC recalculation|
|US8225280||Mar 28, 2008||Jul 17, 2012||International Business Machines Corporation||Incorporating state machine controls into existing non-state machine environments|
|US8233490 *||May 15, 2003||Jul 31, 2012||Telefonaktiebolaget Lm Ericsson (Publ)||Method for the distribution of a network traffic according to SLA and QoS parameters|
|US8238347||Aug 7, 2012||Cisco Technology, Inc.||Fibre channel over ethernet|
|US8255973||Dec 10, 2004||Aug 28, 2012||Chris Hopen||Provisioning remote computers for accessing resources|
|US8259720||Feb 2, 2007||Sep 4, 2012||Cisco Technology, Inc.||Triple-tier anycast addressing|
|US8271694||Aug 26, 2011||Sep 18, 2012||Intel-Ne, Inc.||Method and apparatus for using a single multi-function adapter with different operating systems|
|US8301769||Jun 22, 2010||Oct 30, 2012||Aventail Llc||Classifying an operating environment of a remote computer|
|US8316156||Feb 17, 2006||Nov 20, 2012||Intel-Ne, Inc.||Method and apparatus for interfacing device drivers to single multi-function adapter|
|US8429276||Oct 25, 2010||Apr 23, 2013||Juniper Networks, Inc.||Dynamic resource allocation in virtual environments|
|US8429662||Mar 28, 2008||Apr 23, 2013||International Business Machines Corporation||Passing initiative in a multitasking multiprocessor environment|
|US8432793||Mar 19, 2008||Apr 30, 2013||International Business Machines Corporation||Managing recovery of a link via loss of link|
|US8443066||Jul 7, 2011||May 14, 2013||Oracle International Corporation||Programmatic instantiation, and provisioning of servers|
|US8458280||Dec 22, 2005||Jun 4, 2013||Intel-Ne, Inc.||Apparatus and method for packet transmission over a high speed network supporting remote direct memory access operations|
|US8458390||Mar 26, 2012||Jun 4, 2013||Oracle International Corporation||Methods and systems for handling inter-process and inter-module communications in servers and server clusters|
|US8489778||Aug 17, 2012||Jul 16, 2013||Intel-Ne, Inc.||Method and apparatus for using a single multi-function adapter with different operating systems|
|US8532099||Sep 17, 2010||Sep 10, 2013||Cisco Technology, Inc.||Forwarding table reduction and multipath network forwarding|
|US8565231||May 20, 2011||Oct 22, 2013||Cisco Technology, Inc.||Ethernet extension for the data center|
|US8590032||Oct 14, 2005||Nov 19, 2013||Aventail Llc||Rule-based routing to resources through a network|
|US8601053||Jan 17, 2011||Dec 3, 2013||Oracle International Corporation||Multi-chassis fabric-backplane enterprise servers|
|US8601550||Nov 2, 2010||Dec 3, 2013||Aventail Llc||Remote access to resources over a network|
|US8613041||Jul 30, 2009||Dec 17, 2013||Aventail Llc||Creating rules for routing resource access requests|
|US8615796||Jul 30, 2009||Dec 24, 2013||Aventail Llc||Managing resource allocations|
|US8661158||Mar 7, 2006||Feb 25, 2014||Aventail Llc||Smart tunneling to resources in a network|
|US8699521||Jan 7, 2011||Apr 15, 2014||Intel-Ne, Inc.||Apparatus and method for in-line insertion and removal of markers|
|US8711867 *||Aug 26, 2011||Apr 29, 2014||Sonics, Inc.||Credit flow control scheme in a router with flexible link widths utilizing minimal storage|
|US8713295||Apr 17, 2007||Apr 29, 2014||Oracle International Corporation||Fabric-backplane enterprise servers with pluggable I/O sub-system|
|US8719456||Jan 6, 2011||May 6, 2014||Cisco Technology, Inc.||Shared memory message switch and cache|
|US8743738||Aug 13, 2012||Jun 3, 2014||Cisco Technology, Inc.||Triple-tier anycast addressing|
|US8743872||Jul 9, 2012||Jun 3, 2014||Oracle International Corporation||Storage traffic communication via a switch fabric in accordance with a VLAN|
|US8762125 *||Feb 25, 2008||Jun 24, 2014||International Business Machines Corporation||Emulated multi-tasking multi-processor channels implementing standard network protocols|
|US8792352||May 5, 2011||Jul 29, 2014||Cisco Technology, Inc.||Methods and devices for backward congestion notification|
|US8793699||Mar 19, 2008||Jul 29, 2014||International Business Machines Corporation||Negating initiative for select entries from a shared, strictly FIFO initiative queue|
|US8798038||Aug 26, 2011||Aug 5, 2014||Sonics, Inc.||Efficient header generation in packetized protocols for flexible system on chip architectures|
|US8804529||Jan 24, 2012||Aug 12, 2014||Cisco Technology, Inc.||Backward congestion notification|
|US8842694||Apr 11, 2012||Sep 23, 2014||Cisco Technology, Inc.||Fibre Channel over Ethernet|
|US8848727||Dec 11, 2009||Sep 30, 2014||Oracle International Corporation||Hierarchical transport protocol stack for data transfer between enterprise servers|
|US8868790||Feb 12, 2005||Oct 21, 2014||Oracle International Corporation||Processor-memory module performance acceleration in fabric-backplane enterprise servers|
|US20050010681 *||Jun 3, 2003||Jan 13, 2005||Cisco Technology, Inc. A California Corporation||Computing a path for an open ended uni-directional path protected switched ring|
|US20050132089 *||Mar 1, 2004||Jun 16, 2005||Octigabay Systems Corporation||Directly connected low latency network and interface|
|US20050144481 *||Dec 10, 2004||Jun 30, 2005||Chris Hopen||End point control|
|US20060098589 *||Jun 14, 2005||May 11, 2006||Cisco Technology, Inc.||Forwarding table reduction and multipath network forwarding|
|US20060098681 *||Mar 10, 2005||May 11, 2006||Cisco Technology, Inc.||Fibre channel over Ethernet|
|US20060101140 *||Mar 18, 2005||May 11, 2006||Cisco Technology, Inc.||Ethernet extension for the data center|
|US20060143703 *||Oct 14, 2005||Jun 29, 2006||Chris Hopen||Rule-based routing to resources through a network|
|US20060161970 *||Oct 14, 2005||Jul 20, 2006||Chris Hopen||End point control|
|US20060171318 *||Jun 16, 2005||Aug 3, 2006||Cisco Technology, Inc.||Active queue management methods and devices|
|US20060230119 *||Dec 22, 2005||Oct 12, 2006||Neteffect, Inc.||Apparatus and method for packet transmission over a high speed network supporting remote direct memory access operations|
|US20060251067 *||Apr 6, 2006||Nov 9, 2006||Cisco Technology, Inc., A Corporation Of California||Fibre channel over ethernet|
|US20130051397 *||Aug 26, 2011||Feb 28, 2013||Sonics, Inc.||Credit flow control scheme in a router with flexible link widths utilizing minimal storage|
|US20130254424 *||Mar 15, 2013||Sep 26, 2013||Oracle International Corporation||System and method for providing a scalable signaling mechanism for virtual machine migration in a middleware machine environment|
|CN102075418A *||Dec 31, 2010||May 25, 2011||北京神州绿盟信息安全科技股份有限公司||Network data flow control equipment and method|
|U.S. Classification||709/238, 370/341, 709/249|
|International Classification||G06F15/173, H04L12/56|
|Cooperative Classification||H04L45/586, H04L45/00|
|European Classification||H04L45/00, H04L45/58B|
|Sep 27, 2001||AS||Assignment|
Owner name: INTERNATIONAL BUSINESS MACHINES CORPORATION, NEW Y
Free format text: ASSIGNMENT OF ASSIGNORS INTEREST;ASSIGNORS:CRADDOCK, DAVID F.;ELKO, DAVID ARLEN;GREGG, THOMAS ANTHONY;AND OTHERS;REEL/FRAME:012229/0390;SIGNING DATES FROM 20010921 TO 20010925
|Jan 21, 2010||FPAY||Fee payment|
Year of fee payment: 4
|Mar 28, 2014||REMI||Maintenance fee reminder mailed|
|Jul 11, 2014||SULP||Surcharge for late payment|
Year of fee payment: 7
|Jul 11, 2014||FPAY||Fee payment|
Year of fee payment: 8